Login / Signup

Sequence-to-Sequence Articulatory Inversion Through Time Convolution of Sub-Band Frequency Signals.

Abdolreza Sabzi ShahrebabakiSabato Marco SiniscalchiGiampiero SalviTorbjørn Svendsen
Published in: INTERSPEECH (2020)
Keyphrases
  • subband
  • low frequency
  • high frequency
  • feature vectors
  • image processing
  • multiscale
  • multiresolution
  • speech recognition
  • wavelet coefficients
  • filter bank
  • discrete wavelet transform